| 2024-03-26 09:52:17,497 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 09:52:17,498 Model: "SequenceTagger( | |
| (embeddings): TransformerWordEmbeddings( | |
| (model): BertModel( | |
| (embeddings): BertEmbeddings( | |
| (word_embeddings): Embedding(31103, 768) | |
| (position_embeddings): Embedding(512, 768) | |
| (token_type_embeddings): Embedding(2, 768) | |
| (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (encoder): BertEncoder( | |
| (layer): ModuleList( | |
| (0-11): 12 x BertLayer( | |
| (attention): BertAttention( | |
| (self): BertSelfAttention( | |
| (query): Linear(in_features=768, out_features=768, bias=True) | |
| (key): Linear(in_features=768, out_features=768, bias=True) | |
| (value): Linear(in_features=768, out_features=768, bias=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (output): BertSelfOutput( | |
| (dense): Linear(in_features=768, out_features=768, bias=True) | |
| (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (intermediate): BertIntermediate( | |
| (dense): Linear(in_features=768, out_features=3072, bias=True) | |
| (intermediate_act_fn): GELUActivation() | |
| ) | |
| (output): BertOutput( | |
| (dense): Linear(in_features=3072, out_features=768, bias=True) | |
| (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| ) | |
| ) | |
| (pooler): BertPooler( | |
| (dense): Linear(in_features=768, out_features=768, bias=True) | |
| (activation): Tanh() | |
| ) | |
| ) | |
| ) | |
| (locked_dropout): LockedDropout(p=0.5) | |
| (linear): Linear(in_features=768, out_features=17, bias=True) | |
| (loss_function): CrossEntropyLoss() | |
| )" | |
| 2024-03-26 09:52:17,498 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 09:52:17,498 Corpus: 758 train + 94 dev + 96 test sentences | |
| 2024-03-26 09:52:17,498 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 09:52:17,498 Train: 758 sentences | |
| 2024-03-26 09:52:17,498 (train_with_dev=False, train_with_test=False) | |
| 2024-03-26 09:52:17,498 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 09:52:17,498 Training Params: | |
| 2024-03-26 09:52:17,498 - learning_rate: "3e-05" | |
| 2024-03-26 09:52:17,498 - mini_batch_size: "8" | |
| 2024-03-26 09:52:17,498 - max_epochs: "10" | |
| 2024-03-26 09:52:17,498 - shuffle: "True" | |
| 2024-03-26 09:52:17,498 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 09:52:17,498 Plugins: | |
| 2024-03-26 09:52:17,498 - TensorboardLogger | |
| 2024-03-26 09:52:17,498 - LinearScheduler | warmup_fraction: '0.1' | |
| 2024-03-26 09:52:17,498 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 09:52:17,498 Final evaluation on model from best epoch (best-model.pt) | |
| 2024-03-26 09:52:17,498 - metric: "('micro avg', 'f1-score')" | |
| 2024-03-26 09:52:17,498 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 09:52:17,498 Computation: | |
| 2024-03-26 09:52:17,498 - compute on device: cuda:0 | |
| 2024-03-26 09:52:17,498 - embedding storage: none | |
| 2024-03-26 09:52:17,498 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 09:52:17,498 Model training base path: "flair-co-funer-gbert_base-bs8-e10-lr3e-05-2" | |
| 2024-03-26 09:52:17,498 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 09:52:17,498 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 09:52:17,498 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2024-03-26 09:52:19,319 epoch 1 - iter 9/95 - loss 3.53961513 - time (sec): 1.82 - samples/sec: 1935.43 - lr: 0.000003 - momentum: 0.000000 | |
| 2024-03-26 09:52:21,403 epoch 1 - iter 18/95 - loss 3.35595519 - time (sec): 3.90 - samples/sec: 1845.85 - lr: 0.000005 - momentum: 0.000000 | |
| 2024-03-26 09:52:22,948 epoch 1 - iter 27/95 - loss 3.14534554 - time (sec): 5.45 - samples/sec: 1849.91 - lr: 0.000008 - momentum: 0.000000 | |
| 2024-03-26 09:52:24,870 epoch 1 - iter 36/95 - loss 2.90571609 - time (sec): 7.37 - samples/sec: 1872.40 - lr: 0.000011 - momentum: 0.000000 | |
| 2024-03-26 09:52:26,936 epoch 1 - iter 45/95 - loss 2.71758541 - time (sec): 9.44 - samples/sec: 1806.60 - lr: 0.000014 - momentum: 0.000000 | |
| 2024-03-26 09:52:28,892 epoch 1 - iter 54/95 - loss 2.55098613 - time (sec): 11.39 - samples/sec: 1782.26 - lr: 0.000017 - momentum: 0.000000 | |
| 2024-03-26 09:52:30,410 epoch 1 - iter 63/95 - loss 2.42576159 - time (sec): 12.91 - samples/sec: 1791.76 - lr: 0.000020 - momentum: 0.000000 | |
| 2024-03-26 09:52:31,667 epoch 1 - iter 72/95 - loss 2.29327756 - time (sec): 14.17 - samples/sec: 1845.67 - lr: 0.000022 - momentum: 0.000000 | |
| 2024-03-26 09:52:33,207 epoch 1 - iter 81/95 - loss 2.17212532 - time (sec): 15.71 - samples/sec: 1872.59 - lr: 0.000025 - momentum: 0.000000 | |
| 2024-03-26 09:52:35,142 epoch 1 - iter 90/95 - loss 2.05564105 - time (sec): 17.64 - samples/sec: 1848.21 - lr: 0.000028 - momentum: 0.000000 | |
| 2024-03-26 09:52:36,186 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 09:52:36,186 EPOCH 1 done: loss 1.9901 - lr: 0.000028 | |
| 2024-03-26 09:52:37,129 DEV : loss 0.5836721062660217 - f1-score (micro avg) 0.6361 | |
| 2024-03-26 09:52:37,130 saving best model | |
| 2024-03-26 09:52:37,391 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 09:52:38,699 epoch 2 - iter 9/95 - loss 0.88000104 - time (sec): 1.31 - samples/sec: 2480.75 - lr: 0.000030 - momentum: 0.000000 | |
| 2024-03-26 09:52:40,563 epoch 2 - iter 18/95 - loss 0.74813269 - time (sec): 3.17 - samples/sec: 2166.18 - lr: 0.000029 - momentum: 0.000000 | |
| 2024-03-26 09:52:43,368 epoch 2 - iter 27/95 - loss 0.62424459 - time (sec): 5.98 - samples/sec: 1934.01 - lr: 0.000029 - momentum: 0.000000 | |
| 2024-03-26 09:52:45,428 epoch 2 - iter 36/95 - loss 0.58579327 - time (sec): 8.04 - samples/sec: 1850.08 - lr: 0.000029 - momentum: 0.000000 | |
| 2024-03-26 09:52:47,178 epoch 2 - iter 45/95 - loss 0.54630504 - time (sec): 9.79 - samples/sec: 1836.70 - lr: 0.000028 - momentum: 0.000000 | |
| 2024-03-26 09:52:49,258 epoch 2 - iter 54/95 - loss 0.52267916 - time (sec): 11.87 - samples/sec: 1793.00 - lr: 0.000028 - momentum: 0.000000 | |
| 2024-03-26 09:52:50,788 epoch 2 - iter 63/95 - loss 0.51834858 - time (sec): 13.40 - samples/sec: 1816.83 - lr: 0.000028 - momentum: 0.000000 | |
| 2024-03-26 09:52:52,271 epoch 2 - iter 72/95 - loss 0.50348487 - time (sec): 14.88 - samples/sec: 1843.68 - lr: 0.000028 - momentum: 0.000000 | |
| 2024-03-26 09:52:53,434 epoch 2 - iter 81/95 - loss 0.49372946 - time (sec): 16.04 - samples/sec: 1878.09 - lr: 0.000027 - momentum: 0.000000 | |
| 2024-03-26 09:52:54,709 epoch 2 - iter 90/95 - loss 0.48365737 - time (sec): 17.32 - samples/sec: 1899.73 - lr: 0.000027 - momentum: 0.000000 | |
| 2024-03-26 09:52:55,666 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 09:52:55,666 EPOCH 2 done: loss 0.4715 - lr: 0.000027 | |
| 2024-03-26 09:52:56,562 DEV : loss 0.2874722480773926 - f1-score (micro avg) 0.806 | |
| 2024-03-26 09:52:56,563 saving best model | |
| 2024-03-26 09:52:56,995 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 09:52:59,002 epoch 3 - iter 9/95 - loss 0.25536477 - time (sec): 2.00 - samples/sec: 1660.64 - lr: 0.000026 - momentum: 0.000000 | |
| 2024-03-26 09:53:01,050 epoch 3 - iter 18/95 - loss 0.27949133 - time (sec): 4.05 - samples/sec: 1792.30 - lr: 0.000026 - momentum: 0.000000 | |
| 2024-03-26 09:53:02,010 epoch 3 - iter 27/95 - loss 0.29476589 - time (sec): 5.01 - samples/sec: 1919.91 - lr: 0.000026 - momentum: 0.000000 | |
| 2024-03-26 09:53:03,726 epoch 3 - iter 36/95 - loss 0.28846810 - time (sec): 6.73 - samples/sec: 1885.86 - lr: 0.000025 - momentum: 0.000000 | |
| 2024-03-26 09:53:04,970 epoch 3 - iter 45/95 - loss 0.28835106 - time (sec): 7.97 - samples/sec: 1931.88 - lr: 0.000025 - momentum: 0.000000 | |
| 2024-03-26 09:53:06,994 epoch 3 - iter 54/95 - loss 0.28592424 - time (sec): 10.00 - samples/sec: 1870.19 - lr: 0.000025 - momentum: 0.000000 | |
| 2024-03-26 09:53:08,603 epoch 3 - iter 63/95 - loss 0.27925872 - time (sec): 11.61 - samples/sec: 1880.71 - lr: 0.000025 - momentum: 0.000000 | |
| 2024-03-26 09:53:10,108 epoch 3 - iter 72/95 - loss 0.27217869 - time (sec): 13.11 - samples/sec: 1890.02 - lr: 0.000024 - momentum: 0.000000 | |
| 2024-03-26 09:53:11,883 epoch 3 - iter 81/95 - loss 0.26500557 - time (sec): 14.89 - samples/sec: 1878.07 - lr: 0.000024 - momentum: 0.000000 | |
| 2024-03-26 09:53:14,475 epoch 3 - iter 90/95 - loss 0.24216706 - time (sec): 17.48 - samples/sec: 1871.14 - lr: 0.000024 - momentum: 0.000000 | |
| 2024-03-26 09:53:15,563 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 09:53:15,563 EPOCH 3 done: loss 0.2400 - lr: 0.000024 | |
| 2024-03-26 09:53:16,458 DEV : loss 0.23845794796943665 - f1-score (micro avg) 0.8729 | |
| 2024-03-26 09:53:16,459 saving best model | |
| 2024-03-26 09:53:16,886 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 09:53:18,564 epoch 4 - iter 9/95 - loss 0.19907058 - time (sec): 1.68 - samples/sec: 1917.48 - lr: 0.000023 - momentum: 0.000000 | |
| 2024-03-26 09:53:20,539 epoch 4 - iter 18/95 - loss 0.18225053 - time (sec): 3.65 - samples/sec: 1844.67 - lr: 0.000023 - momentum: 0.000000 | |
| 2024-03-26 09:53:21,759 epoch 4 - iter 27/95 - loss 0.17780171 - time (sec): 4.87 - samples/sec: 1932.07 - lr: 0.000022 - momentum: 0.000000 | |
| 2024-03-26 09:53:23,404 epoch 4 - iter 36/95 - loss 0.17396565 - time (sec): 6.52 - samples/sec: 1904.99 - lr: 0.000022 - momentum: 0.000000 | |
| 2024-03-26 09:53:25,531 epoch 4 - iter 45/95 - loss 0.17094092 - time (sec): 8.64 - samples/sec: 1847.31 - lr: 0.000022 - momentum: 0.000000 | |
| 2024-03-26 09:53:27,044 epoch 4 - iter 54/95 - loss 0.17620156 - time (sec): 10.16 - samples/sec: 1858.30 - lr: 0.000022 - momentum: 0.000000 | |
| 2024-03-26 09:53:29,472 epoch 4 - iter 63/95 - loss 0.16912771 - time (sec): 12.58 - samples/sec: 1811.77 - lr: 0.000021 - momentum: 0.000000 | |
| 2024-03-26 09:53:31,951 epoch 4 - iter 72/95 - loss 0.15886167 - time (sec): 15.06 - samples/sec: 1775.85 - lr: 0.000021 - momentum: 0.000000 | |
| 2024-03-26 09:53:33,379 epoch 4 - iter 81/95 - loss 0.15583393 - time (sec): 16.49 - samples/sec: 1782.01 - lr: 0.000021 - momentum: 0.000000 | |
| 2024-03-26 09:53:35,144 epoch 4 - iter 90/95 - loss 0.15591548 - time (sec): 18.26 - samples/sec: 1781.89 - lr: 0.000020 - momentum: 0.000000 | |
| 2024-03-26 09:53:36,253 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 09:53:36,253 EPOCH 4 done: loss 0.1525 - lr: 0.000020 | |
| 2024-03-26 09:53:37,151 DEV : loss 0.20792341232299805 - f1-score (micro avg) 0.8679 | |
| 2024-03-26 09:53:37,152 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 09:53:38,113 epoch 5 - iter 9/95 - loss 0.09800132 - time (sec): 0.96 - samples/sec: 2144.46 - lr: 0.000020 - momentum: 0.000000 | |
| 2024-03-26 09:53:39,777 epoch 5 - iter 18/95 - loss 0.10274591 - time (sec): 2.62 - samples/sec: 2027.83 - lr: 0.000019 - momentum: 0.000000 | |
| 2024-03-26 09:53:42,223 epoch 5 - iter 27/95 - loss 0.10010196 - time (sec): 5.07 - samples/sec: 1797.73 - lr: 0.000019 - momentum: 0.000000 | |
| 2024-03-26 09:53:44,045 epoch 5 - iter 36/95 - loss 0.10033903 - time (sec): 6.89 - samples/sec: 1799.99 - lr: 0.000019 - momentum: 0.000000 | |
| 2024-03-26 09:53:45,998 epoch 5 - iter 45/95 - loss 0.09981141 - time (sec): 8.85 - samples/sec: 1766.90 - lr: 0.000019 - momentum: 0.000000 | |
| 2024-03-26 09:53:47,592 epoch 5 - iter 54/95 - loss 0.10391988 - time (sec): 10.44 - samples/sec: 1804.89 - lr: 0.000018 - momentum: 0.000000 | |
| 2024-03-26 09:53:49,927 epoch 5 - iter 63/95 - loss 0.10398408 - time (sec): 12.77 - samples/sec: 1792.95 - lr: 0.000018 - momentum: 0.000000 | |
| 2024-03-26 09:53:51,331 epoch 5 - iter 72/95 - loss 0.11093906 - time (sec): 14.18 - samples/sec: 1811.66 - lr: 0.000018 - momentum: 0.000000 | |
| 2024-03-26 09:53:53,221 epoch 5 - iter 81/95 - loss 0.10674185 - time (sec): 16.07 - samples/sec: 1787.12 - lr: 0.000017 - momentum: 0.000000 | |
| 2024-03-26 09:53:55,065 epoch 5 - iter 90/95 - loss 0.10551264 - time (sec): 17.91 - samples/sec: 1789.51 - lr: 0.000017 - momentum: 0.000000 | |
| 2024-03-26 09:53:56,407 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 09:53:56,407 EPOCH 5 done: loss 0.1066 - lr: 0.000017 | |
| 2024-03-26 09:53:57,304 DEV : loss 0.1804860234260559 - f1-score (micro avg) 0.9197 | |
| 2024-03-26 09:53:57,305 saving best model | |
| 2024-03-26 09:53:57,730 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 09:53:59,105 epoch 6 - iter 9/95 - loss 0.07972278 - time (sec): 1.37 - samples/sec: 2096.57 - lr: 0.000016 - momentum: 0.000000 | |
| 2024-03-26 09:54:01,256 epoch 6 - iter 18/95 - loss 0.08118019 - time (sec): 3.52 - samples/sec: 2035.01 - lr: 0.000016 - momentum: 0.000000 | |
| 2024-03-26 09:54:02,812 epoch 6 - iter 27/95 - loss 0.07772860 - time (sec): 5.08 - samples/sec: 1976.72 - lr: 0.000016 - momentum: 0.000000 | |
| 2024-03-26 09:54:04,780 epoch 6 - iter 36/95 - loss 0.07928132 - time (sec): 7.05 - samples/sec: 1915.68 - lr: 0.000016 - momentum: 0.000000 | |
| 2024-03-26 09:54:06,910 epoch 6 - iter 45/95 - loss 0.08814070 - time (sec): 9.18 - samples/sec: 1935.68 - lr: 0.000015 - momentum: 0.000000 | |
| 2024-03-26 09:54:08,096 epoch 6 - iter 54/95 - loss 0.08402558 - time (sec): 10.36 - samples/sec: 1950.71 - lr: 0.000015 - momentum: 0.000000 | |
| 2024-03-26 09:54:09,157 epoch 6 - iter 63/95 - loss 0.08522702 - time (sec): 11.42 - samples/sec: 1970.67 - lr: 0.000015 - momentum: 0.000000 | |
| 2024-03-26 09:54:10,682 epoch 6 - iter 72/95 - loss 0.07933407 - time (sec): 12.95 - samples/sec: 1971.66 - lr: 0.000014 - momentum: 0.000000 | |
| 2024-03-26 09:54:12,675 epoch 6 - iter 81/95 - loss 0.07836560 - time (sec): 14.94 - samples/sec: 1956.42 - lr: 0.000014 - momentum: 0.000000 | |
| 2024-03-26 09:54:14,661 epoch 6 - iter 90/95 - loss 0.07745159 - time (sec): 16.93 - samples/sec: 1942.78 - lr: 0.000014 - momentum: 0.000000 | |
| 2024-03-26 09:54:15,584 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 09:54:15,584 EPOCH 6 done: loss 0.0758 - lr: 0.000014 | |
| 2024-03-26 09:54:16,481 DEV : loss 0.16234630346298218 - f1-score (micro avg) 0.9135 | |
| 2024-03-26 09:54:16,482 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 09:54:17,909 epoch 7 - iter 9/95 - loss 0.04375441 - time (sec): 1.43 - samples/sec: 1863.36 - lr: 0.000013 - momentum: 0.000000 | |
| 2024-03-26 09:54:19,705 epoch 7 - iter 18/95 - loss 0.06014365 - time (sec): 3.22 - samples/sec: 1798.11 - lr: 0.000013 - momentum: 0.000000 | |
| 2024-03-26 09:54:21,311 epoch 7 - iter 27/95 - loss 0.05965848 - time (sec): 4.83 - samples/sec: 1889.05 - lr: 0.000013 - momentum: 0.000000 | |
| 2024-03-26 09:54:23,028 epoch 7 - iter 36/95 - loss 0.05912689 - time (sec): 6.55 - samples/sec: 1837.26 - lr: 0.000012 - momentum: 0.000000 | |
| 2024-03-26 09:54:24,390 epoch 7 - iter 45/95 - loss 0.05753334 - time (sec): 7.91 - samples/sec: 1854.27 - lr: 0.000012 - momentum: 0.000000 | |
| 2024-03-26 09:54:26,446 epoch 7 - iter 54/95 - loss 0.05727675 - time (sec): 9.96 - samples/sec: 1799.19 - lr: 0.000012 - momentum: 0.000000 | |
| 2024-03-26 09:54:28,682 epoch 7 - iter 63/95 - loss 0.05724513 - time (sec): 12.20 - samples/sec: 1749.98 - lr: 0.000011 - momentum: 0.000000 | |
| 2024-03-26 09:54:31,233 epoch 7 - iter 72/95 - loss 0.06278608 - time (sec): 14.75 - samples/sec: 1747.69 - lr: 0.000011 - momentum: 0.000000 | |
| 2024-03-26 09:54:33,184 epoch 7 - iter 81/95 - loss 0.06518938 - time (sec): 16.70 - samples/sec: 1754.83 - lr: 0.000011 - momentum: 0.000000 | |
| 2024-03-26 09:54:35,156 epoch 7 - iter 90/95 - loss 0.06685056 - time (sec): 18.67 - samples/sec: 1755.32 - lr: 0.000010 - momentum: 0.000000 | |
| 2024-03-26 09:54:36,048 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 09:54:36,048 EPOCH 7 done: loss 0.0653 - lr: 0.000010 | |
| 2024-03-26 09:54:36,945 DEV : loss 0.17551575601100922 - f1-score (micro avg) 0.9174 | |
| 2024-03-26 09:54:36,946 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 09:54:39,192 epoch 8 - iter 9/95 - loss 0.06359199 - time (sec): 2.25 - samples/sec: 1687.40 - lr: 0.000010 - momentum: 0.000000 | |
| 2024-03-26 09:54:40,736 epoch 8 - iter 18/95 - loss 0.06088028 - time (sec): 3.79 - samples/sec: 1818.42 - lr: 0.000010 - momentum: 0.000000 | |
| 2024-03-26 09:54:42,902 epoch 8 - iter 27/95 - loss 0.06545372 - time (sec): 5.96 - samples/sec: 1775.32 - lr: 0.000009 - momentum: 0.000000 | |
| 2024-03-26 09:54:44,443 epoch 8 - iter 36/95 - loss 0.06062523 - time (sec): 7.50 - samples/sec: 1799.86 - lr: 0.000009 - momentum: 0.000000 | |
| 2024-03-26 09:54:46,311 epoch 8 - iter 45/95 - loss 0.05645313 - time (sec): 9.36 - samples/sec: 1777.81 - lr: 0.000009 - momentum: 0.000000 | |
| 2024-03-26 09:54:47,991 epoch 8 - iter 54/95 - loss 0.05908816 - time (sec): 11.04 - samples/sec: 1788.68 - lr: 0.000008 - momentum: 0.000000 | |
| 2024-03-26 09:54:49,789 epoch 8 - iter 63/95 - loss 0.05709152 - time (sec): 12.84 - samples/sec: 1788.13 - lr: 0.000008 - momentum: 0.000000 | |
| 2024-03-26 09:54:51,097 epoch 8 - iter 72/95 - loss 0.05568644 - time (sec): 14.15 - samples/sec: 1807.94 - lr: 0.000008 - momentum: 0.000000 | |
| 2024-03-26 09:54:52,919 epoch 8 - iter 81/95 - loss 0.05439142 - time (sec): 15.97 - samples/sec: 1833.11 - lr: 0.000007 - momentum: 0.000000 | |
| 2024-03-26 09:54:55,325 epoch 8 - iter 90/95 - loss 0.05191514 - time (sec): 18.38 - samples/sec: 1794.74 - lr: 0.000007 - momentum: 0.000000 | |
| 2024-03-26 09:54:56,129 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 09:54:56,129 EPOCH 8 done: loss 0.0526 - lr: 0.000007 | |
| 2024-03-26 09:54:57,031 DEV : loss 0.18304860591888428 - f1-score (micro avg) 0.9193 | |
| 2024-03-26 09:54:57,032 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 09:54:58,782 epoch 9 - iter 9/95 - loss 0.06565949 - time (sec): 1.75 - samples/sec: 1941.54 - lr: 0.000007 - momentum: 0.000000 | |
| 2024-03-26 09:55:01,043 epoch 9 - iter 18/95 - loss 0.04730623 - time (sec): 4.01 - samples/sec: 1728.97 - lr: 0.000006 - momentum: 0.000000 | |
| 2024-03-26 09:55:02,922 epoch 9 - iter 27/95 - loss 0.05364398 - time (sec): 5.89 - samples/sec: 1771.72 - lr: 0.000006 - momentum: 0.000000 | |
| 2024-03-26 09:55:04,461 epoch 9 - iter 36/95 - loss 0.05374813 - time (sec): 7.43 - samples/sec: 1786.99 - lr: 0.000006 - momentum: 0.000000 | |
| 2024-03-26 09:55:05,866 epoch 9 - iter 45/95 - loss 0.04853111 - time (sec): 8.83 - samples/sec: 1826.08 - lr: 0.000005 - momentum: 0.000000 | |
| 2024-03-26 09:55:07,268 epoch 9 - iter 54/95 - loss 0.04542395 - time (sec): 10.24 - samples/sec: 1879.04 - lr: 0.000005 - momentum: 0.000000 | |
| 2024-03-26 09:55:09,076 epoch 9 - iter 63/95 - loss 0.04888173 - time (sec): 12.04 - samples/sec: 1887.19 - lr: 0.000005 - momentum: 0.000000 | |
| 2024-03-26 09:55:11,075 epoch 9 - iter 72/95 - loss 0.04857160 - time (sec): 14.04 - samples/sec: 1860.12 - lr: 0.000004 - momentum: 0.000000 | |
| 2024-03-26 09:55:13,343 epoch 9 - iter 81/95 - loss 0.04878537 - time (sec): 16.31 - samples/sec: 1819.63 - lr: 0.000004 - momentum: 0.000000 | |
| 2024-03-26 09:55:15,069 epoch 9 - iter 90/95 - loss 0.04736803 - time (sec): 18.04 - samples/sec: 1835.02 - lr: 0.000004 - momentum: 0.000000 | |
| 2024-03-26 09:55:15,655 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 09:55:15,655 EPOCH 9 done: loss 0.0468 - lr: 0.000004 | |
| 2024-03-26 09:55:16,548 DEV : loss 0.17421986162662506 - f1-score (micro avg) 0.9209 | |
| 2024-03-26 09:55:16,549 saving best model | |
| 2024-03-26 09:55:16,974 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 09:55:19,020 epoch 10 - iter 9/95 - loss 0.01627610 - time (sec): 2.04 - samples/sec: 1889.72 - lr: 0.000003 - momentum: 0.000000 | |
| 2024-03-26 09:55:20,773 epoch 10 - iter 18/95 - loss 0.03077255 - time (sec): 3.80 - samples/sec: 1870.99 - lr: 0.000003 - momentum: 0.000000 | |
| 2024-03-26 09:55:21,875 epoch 10 - iter 27/95 - loss 0.02772412 - time (sec): 4.90 - samples/sec: 1944.17 - lr: 0.000003 - momentum: 0.000000 | |
| 2024-03-26 09:55:23,321 epoch 10 - iter 36/95 - loss 0.03377579 - time (sec): 6.34 - samples/sec: 1973.31 - lr: 0.000002 - momentum: 0.000000 | |
| 2024-03-26 09:55:25,258 epoch 10 - iter 45/95 - loss 0.03917926 - time (sec): 8.28 - samples/sec: 1905.99 - lr: 0.000002 - momentum: 0.000000 | |
| 2024-03-26 09:55:26,345 epoch 10 - iter 54/95 - loss 0.04335361 - time (sec): 9.37 - samples/sec: 1953.72 - lr: 0.000002 - momentum: 0.000000 | |
| 2024-03-26 09:55:27,567 epoch 10 - iter 63/95 - loss 0.04067493 - time (sec): 10.59 - samples/sec: 1981.28 - lr: 0.000001 - momentum: 0.000000 | |
| 2024-03-26 09:55:29,473 epoch 10 - iter 72/95 - loss 0.04059246 - time (sec): 12.50 - samples/sec: 1975.98 - lr: 0.000001 - momentum: 0.000000 | |
| 2024-03-26 09:55:32,107 epoch 10 - iter 81/95 - loss 0.03957121 - time (sec): 15.13 - samples/sec: 1935.90 - lr: 0.000001 - momentum: 0.000000 | |
| 2024-03-26 09:55:34,114 epoch 10 - iter 90/95 - loss 0.03941973 - time (sec): 17.14 - samples/sec: 1914.50 - lr: 0.000000 - momentum: 0.000000 | |
| 2024-03-26 09:55:35,030 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 09:55:35,030 EPOCH 10 done: loss 0.0395 - lr: 0.000000 | |
| 2024-03-26 09:55:35,932 DEV : loss 0.17624321579933167 - f1-score (micro avg) 0.9248 | |
| 2024-03-26 09:55:35,933 saving best model | |
| 2024-03-26 09:55:36,648 ---------------------------------------------------------------------------------------------------- | |
| 2024-03-26 09:55:36,649 Loading model from best epoch ... | |
| 2024-03-26 09:55:37,535 SequenceTagger predicts: Dictionary with 17 tags: O, S-Unternehmen, B-Unternehmen, E-Unternehmen, I-Unternehmen, S-Auslagerung, B-Auslagerung, E-Auslagerung, I-Auslagerung, S-Ort, B-Ort, E-Ort, I-Ort, S-Software, B-Software, E-Software, I-Software | |
| 2024-03-26 09:55:38,304 | |
| Results: | |
| - F-score (micro) 0.907 | |
| - F-score (macro) 0.69 | |
| - Accuracy 0.8357 | |
| By class: | |
| precision recall f1-score support | |
| Unternehmen 0.9180 0.8835 0.9004 266 | |
| Auslagerung 0.8470 0.9116 0.8781 249 | |
| Ort 0.9708 0.9925 0.9815 134 | |
| Software 0.0000 0.0000 0.0000 0 | |
| micro avg 0.8974 0.9168 0.9070 649 | |
| macro avg 0.6839 0.6969 0.6900 649 | |
| weighted avg 0.9017 0.9168 0.9086 649 | |
| 2024-03-26 09:55:38,304 ---------------------------------------------------------------------------------------------------- | |